whatmodel.sh / image / Ideogram 3.0

Ideogram 3.0

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Ideogram 3.0 is a closed-weights image model from Ideogram, released March 2025. Licence: proprietary.

51.9±2.0#76 of 144 image modelsfrom 3 benchmark results across 3 sources

Score within the LMArena text-to-image comparison set only.

$ how it compares

The image models ranked either side of Ideogram 3.0, out of 197 with a score, then more from Ideogram.

#modelscorewhereRAMreleased
92Wan 2.5 Image-to-Image Preview Alibaba53±4api $0.030/image2025-09
93MiniMax image-01 MiniMax53±5api $0.0035/image
94Ideogram 3.0 Ideogram52±2api $0.060/image2025-03
95UniPic 3 Skywork AI52±3comparison only2026-01
96Imagen 3 (imagen-3.0-generate-002) Google52±2comparison only2025-01
more from Ideogram
19Ideogram 4.5 Ideogram68±3comparison only
23Ideogram 4.0 Ideogram66±2api $0.060/image +local~6.1GB2026-06
118Ideogram 2.0 Ideogram46±2api $0.080/image

see all image models · find the ones that fit your machine

$ what it's good at

text to image▂▅▅▃▄▄█▃▁▂▁▁ #64 of 126 * · 82% of its score · 2 tests
testresultvs the others in its rundifficultycountswhy
LMArena text-to-image1048.4 ✎▂▂▃▄▇█▄▂▄▂·▂ beats 15/75avg 1027▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 62%typical
ServImage task acceptance (human payment decisions, commercial design tasks)25.9% ✎▂▃··▂··▃█··▂ beats 5/11hard · avg 18%▇▇▇▇▇▇▇▇ 21%sharp
image to image / editing▁▁·▃▂▃█▃▃▄▁▁ #45 of 62 * · 21% of its score · 1 test

Beats GPT Image 1 Mini, FLUX.1 Kontext [max], Qwen-Image here, though they rank higher overall. Trails GLM-Image, FLUX.2 [klein] 4B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
ServImage task acceptance (human payment decisions, commercial design tasks)25.9% ✎▂▃··▂··▃█··▂ beats 5/11hard · avg 18%▇▇▇▇▇▇▇▇ 21%sharp
other tests1 not in a task · 16% of its score
testresultvs the others in its rundifficultycountswhy
Rapidata human-face generation alignment (Elo)962.9 ✎▃··▅▃··▃▃··█ beats 2/8avg 1012▇▇▇▇▇▇ 16%typical

$ where to run it

Through an API

api · fal.ai · $0.060/image · fal.ai ↗ · price sourceUSD per generated image, Ideogram 3 BALANCED setting on fal.ai. TURBO/QUALITY excluded. Product: Ideogram 3 text-to-image. API model: fal-ai/ideogram/v3. Settings: rendering speed=BALANCED, n=1. Price basis: published rate. Currency: USD.

$ how the score was worked out · LMArena leaderboard dataset 62%, ServImage: An Image Generatio… 21%, Rapidata/Face_Generation_Benc… 16%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
LMArena leaderboard dataset1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 62%CC BY 4.0
ServImage: An Image Generation and Editing Benchmark from Real-world Commercial Imaging Services (arXiv:2604.24023v2)1▇▇▇▇▇▇ 21%CC-BY-4.0
Rapidata/Face_Generation_Benchmark (Human Face Generation Alignment) published dataset-card leaderboard1▇▇▇▇▇ 16%CDLA-Permissive-2.0
prior · pull toward the middle▇ 2%
weighted average= 51.9

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json